RESUMEN
The geometric designs of MEMS devices can profoundly impact their physical properties and eventual performances. However, it is challenging for researchers to rationally consider a large number of possible designs, as it would be very time- and resource-consuming to study all these cases using numerical simulation. In this paper, we report the use of deep learning techniques to accelerate the MEMS design cycle by quickly and accurately predicting the physical properties of numerous design candidates with vastly different geometric features. Design candidates are represented in a nonparameterized, topologically unconstrained form using pixelated black-and-white images. After sufficient training, a deep neural network can quickly calculate the physical properties of interest with good accuracy without using conventional numerical tools such as finite element analysis. As an example, we apply our deep learning approach in the prediction of the modal frequency and quality factor of disk-shaped microscale resonators. With reasonable training, our deep learning neural network becomes a high-speed, high-accuracy calculator: it can identify the flexural mode frequency and the quality factor 4.6 × 103 times and 2.6 × 104 times faster, respectively, than conventional numerical simulation packages, with good accuracies of 98.8 ± 1.6% and 96.8 ± 3.1%, respectively. When simultaneously predicting the frequency and the quality factor, up to ~96.0% of the total computation time can be saved during the design process. The proposed technique can rapidly screen over thousands of design candidates and promotes experience-free and data-driven MEMS structural designs.
RESUMEN
INTRODUCTION: The most frequently prescribed analgesic drugs in primary care centers in Turkey are diclofenac and paracetamol, respectively. In this study, we aimed to compare paracetamol-included prescriptions (PIP) and diclofenac-included prescriptions (DIP) generated for adult patients in primary care. METHODS: In this cross-sectional study, PIPs (n = 280 488) and DIPs (n = 337 935) created for adults by systematic sampling among primary care physicians working in Istanbul in 2016 (n = 1431) were examined. The demographic characteristics, diagnoses, and additional drugs in PIPs and DIPs were compared. RESULTS: Women constituted the majority in both groups (69.8% and 67.9%, respectively; P < 0.05), and mean age at PIP (52.6 ± 18.8 years) was lower compared to DIP (56.3 ± 16.1 years), (P < 0.05). In single-diagnosis prescriptions, 11 of the 15 most common diagnoses in PIP were respiratory tract infections (47.9%); three pain-related diagnoses formed 4.6% of all these prescriptions. In DIP, the number of pain-related diagnoses, mostly of musculoskeletal origin, was eight (28.5%); four diagnoses (7.8%) were upper respiratory tract infections. While hypertension was the third most common diagnosis in PIP (6.1%), it was ranked first in DIP (8.0%). The percentage of prescriptions with additional analgesic (14.0% versus 18.3%, P < 0.001), proton-pump inhibitor (13.8% versus 18.4%; P < 0.001), and antihypertensive (22.0% versus 24.8%, P < 0.001) was lower in PIP compared to DIP. However, the percentage of prescriptions with antibiotics (31.3% versus 14.7%, P < 0.001) was higher in PIP. CONCLUSION: Paracetamol appears to be preferred mostly in upper respiratory tract infections compared to the preference of diclofenac rather in painful/inflammatory musculoskeletal conditions. The presence of hypertension among the most commonly encountered diagnoses for these analgesic drugs points to challenges in establishing the diagnosing-treatment match and indicates potential irrational prescribing practice, especially for interactions.
